{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-llm-language-network-a-neuroscientific","title":"The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units","arxiv_id":"2411.02280","date":"2024-11-04","proceeding":null,"authors":["Badr AlKhamissi","Greta Tuckute","Antoine Bosselut","Martin Schrimpf"],"abstract":"Large language models (LLMs) exhibit remarkable capabilities on not just language tasks, but also various tasks that are not linguistic in nature, such as logical reasoning and social inference. In the human brain, neuroscience has identified a core language system that selectively and causally supports language processing. We here ask whether similar specialization for language emerges in LLMs. We identify language-selective units within 18 popular LLMs, using the same localization approach that is used in neuroscience. We then establish the causal role of these units by demonstrating that ablating LLM language-selective units -- but not random units -- leads to drastic deficits in language tasks. Correspondingly, language-selective LLM units are more aligned to brain recordings from the human language system than random units. Finally, we investigate whether our localization method extends to other cognitive domains: while we find specialized networks in some LLMs for reasoning and social capabilities, there are substantial differences among models. These findings provide functional and causal evidence for specialization in large language models, and highlight parallels with the functional organization in the brain.","url_abs":"https://arxiv.org/abs/2411.02280v1","url_pdf":"https://arxiv.org/pdf/2411.02280v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-llm-language-network-a-neuroscientific","repo_url":"https://github.com/bkhmsi/llm-localization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.02280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02280"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bkhmsi/llm-localization","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"models/modeling_gemma.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/models/modeling_gemma.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"bac65c3dafaec040","entry":"apply_rotary_pos_emb","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"models/modeling_falcon.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/models/modeling_falcon.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bac65c3dafaec040"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"models/modeling_falcon.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/models/modeling_falcon.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"b4acc4f0962c97ca","entry":"build_alibi_tensor","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"models/modeling_falcon.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/models/modeling_falcon.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4acc4f0962c97ca"}},{"code_sha256_prefix":"267bae0b82b6aceb","entry":"get_hidden_dim","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"267bae0b82b6aceb"}},{"code_sha256_prefix":"4cef83f93d686f92","entry":"get_layer_names","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cef83f93d686f92"}},{"code_sha256_prefix":"18f9d02a5c566c5e","entry":"get_num_blocks","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"18f9d02a5c566c5e"}},{"code_sha256_prefix":"eae14ebac1cd9c52","entry":"load_tf_weights_in_gpt2","repo":"bkhmsi/llm-localization","repo_kind":"official","path":"models/modeling_gpt2.py","file_url":"https://github.com/bkhmsi/llm-localization/blob/HEAD/models/modeling_gpt2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eae14ebac1cd9c52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}